© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 48360
    Prev
    Next
    INDEX
    Explanations

    saliva production and function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    0.70
     JFK
    0.70
    k
    0.68
     American
    0.66
     Cinema
    0.64
     Winner
    0.64
     DC
    0.64
     World
    0.62
    \
    0.61
     URI
    0.61
    POSITIVE LOGITS
    на
    0.85
    }$\
    0.73
     sẽ
    0.73
    ۱
    0.73
    ILE
    0.72
     වල
    0.72
    лети
    0.71
    يلي
    0.71
    ය
    0.71
    蚓
    0.70
    Activations Density 0.000%

    No Known Activations